Update app.py

app.py

@@ -7,7 +7,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # Load model and tokenizer if a GPU is available
 if torch.cuda.is_available():
-    model_id = "allenai/OLMo-7B-Instruct"
+    model_id = "allenai/OLMo-7B-hf"
     adapters_name = "yilunzhao/olmo-finetuned"
     model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True)
     model = PeftModel.from_pretrained(model, adapters_name)